Machine learning for physical layer link adaptation in multiple-antenna wireless networks
Robert C. Daniels, Ketan Mandke, Steven W. Peters, Scott Nettles, Robert W. Heath · 2008
Prototyping and experimentation are key to understanding the operation of wireless systems in practice. In this extended abstract we present an implementation of physical layer link adaptation, or data rate selection, through machine learning on Hydra: an IEEE 802.11n draft standard multihop wireless networking prototype. This implementation highlights both the utility of learning-based link adaptation in practical networks as well as the flexibility of Hydra.